A System to Construct an Interest Model of User Based on Information in Browsed Web Page by User

  • Kosuke Kawazu
  • Masakazu Murao
  • Takeru Ohta
  • Masayoshi Mase
  • Takashi Maeno
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5612)


In these days, they expect that computers comprehend characteristics of the user, for example interest and liking, to interact with computers. In this study, we constructed a system to construct an interest model of the user based on information in browsed Web pages by the user by extracting words and interword relationships. In this model, metadata is appended to words and interword relationships. Kinds of metadata of words are six, personal name, corporate name, site name, name of commodity, product name and location name. And metadata of interword relationships is prepared to clarify relationships of these words. This system makes a map by visualizing this model. And this system has functions to zoom and modify this map. We showed efficacy of this system by using evaluation experiment.


Occurrence Rate Concordance Rate Word Examinee Evaluation Item Content Rate 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Huangr, H., Fujii, A., Ishikawa, T.: The individualized technique of the information retrieval based on the Web community. In: The Association for Natural Language Processing Annual Conference, vol. 11, pp. 1006–1009 (2005)Google Scholar
  2. 2.
    Niwa, S., Doi, T., Honiden, S.: Web Page Recommender System Based on Folksonomy Mining. Transactions of information Processing Society of Japan 47(5), 1382–1392 (2006)Google Scholar
  3. 3.
    Kazienko, P., Kiewra, M.: Integration of relational databases and Web site content for product and page recommendation. In: Database Engineering and Applications Symposium, IDEAAS (2004)Google Scholar
  4. 4.
    Golovin, N., Rahm, E.: Reinforcement Learning Architecture for Web Recommendation. In: Proceedings of the International Conference on Information (2004)Google Scholar
  5. 5.
    Claypool, M., Gokhale, A., Miranda, T., et al.: Combining Content-Based and Collaborative Filters in an Online. In: Proc. ACM SIGIR 1999 Workshop on Recommender Systems: Algorithms and Evaluation, Berkeley, California (1999)Google Scholar
  6. 6.
    Hijikata, Y.: User Profiling Technique for Information Recommendation and Information Filtering. Journal of Japanese Society for Artificial Intelligence 15(5), 489–497 (2003)Google Scholar
  7. 7.
    Kantor, P.B., Boros, E., Melamed, B.: Capturing Human Intelligence in the Net. Communications of the ACM 43(8), 112–115 (2000)CrossRefGoogle Scholar
  8. 8.
    Anderson, C.R., Horvitz, E.: Web Montage: A Dynamic Personalized Start Page. In: Proceedings of the 11th World Wide Web Conference (WWW’s 2002) (2002)Google Scholar
  9. 9.
    Murata, T., Saito, K.: Extraction and Visualization of Web Users’ Interests Using Site-Keyword Graphs. Journal of Japan Society for Fuzzy Theory and Intelligent informatics 18(5), 701–710 (2006)CrossRefGoogle Scholar
  10. 10.
  11. 11.
  12. 12.
  13. 13.
  14. 14.
    Takashiro, T., Takeda, H.: Acquisition and Organaization of Personal Knowledge through WWW Browsing. Institute of Electronics, Information, and Communication Engineers J85-D-1(6), 549–559 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Kosuke Kawazu
    • 1
  • Masakazu Murao
    • 2
  • Takeru Ohta
    • 3
  • Masayoshi Mase
    • 3
  • Takashi Maeno
    • 2
  1. 1.Graduate School of System Design and ManagementKeio UniversityYokohamaJapan
  2. 2.Graduate School of System Design and ManagementKeio UniversityJapan
  3. 3.Keywalker. Inc Email: do-my-best@a6.keio.jpTokyoJapan

Personalised recommendations